Related papers: The Missing Piece in Complex Analytics: Low Latenc…
The cloud computing paradigm underlines data center and telecommunication infrastructure design. Heavily leveraging virtualization, it slices hardware and software resources into smaller software units for greater flexibility of…
Large Language Models (LLMs) in agentic workflows combine multi-step reasoning, heterogeneous tool use, and collaboration across multiple specialized agents. Existing LLM serving engines optimize individual calls in isolation, while…
In today's world of advanced AI technologies, data management is a critical component of any AI/ML solution. Effective data management is vital for the creation and maintenance of high-quality, diverse datasets, which significantly enhance…
Network Virtualization is one of the key technologies for developing the future mobile networks. However, the performance of virtual mobile entities may not be sufficient for delivering the service required for future networks in terms of…
While deep learning models have replaced hand-designed features across many domains, these models are still trained with hand-designed optimizers. In this work, we leverage the same scaling approach behind the success of deep learning to…
Despite the remarkable progress of large language models (LLMs), the capabilities of standalone LLMs have begun to plateau when tackling real-world, complex tasks that require interaction with external tools and dynamic environments.…
Data plays a fundamental role in training Large Language Models (LLMs). Efficient data management, particularly in formulating a well-suited training dataset, is significant for enhancing model performance and improving training efficiency…
The last decade witnessed a rise in the importance of supervised learning applications involving {\em big data} and {\em big models}. Big data refers to situations where the amounts of training data available and needed causes difficulties…
Large language models (LLMs) have shown remarkable success in recent years, enabling a wide range of applications, including intelligent assistants that support users' daily life and work. A critical factor in building such assistants is…
The pre-trained Large Language Models (LLMs) can be adapted for many downstream tasks and tailored to align with human preferences through fine-tuning. Recent studies have discovered that LLMs can achieve desirable performance with only a…
This paper presents the SLEGO (Software-Lego) system, a collaborative analytics platform that bridges the gap between experienced developers and novice users using a cloud-based platform with modular, reusable microservices. These…
Streaming analysis is widely used in cloud as well as edge infrastructures. In these contexts, fine-grained application performance can be based on accurate modeling of streaming operators. This is especially beneficial for computationally…
AI agents are emerging as a dominant workload in a wide range of applications, promising to be the vehicle that delivers the promised benefits of AI to enterprises and consumers. Unlike conventional software or static inference, agentic…
Dynamic Data selection aims to accelerate training by prioritizing informative samples during online training. However, existing methods typically rely on task-specific handcrafted metrics or static/snapshot-based criteria to estimate…
Serverless computing, commonly offered as Function-as-a-Service, was initially designed for small, lean applications. However, there has been an increasing desire to run larger, more complex applications (what we call bulky applications) in…
Legal exploration, analysis, and interpretation remain complex and demanding tasks, even for experienced legal scholars, due to the domain-specific language, tacit legal concepts, and intentional ambiguities embedded in legal texts. In…
How can the complexity of ML-enabled systems be managed effectively? The goal of this research is to investigate how complexity affects ML-Enabled Systems (MLES). To address this question, this research aims to introduce a metrics-based…
Objective. We propose an approach to reason about goals, obstacles, and to select suitable big data solution architecture that satisfy quality goal preferences and constraints of stakeholders at the presence of the decision outcome…
Event sequence data record series of discrete events in the time order of occurrence. They are commonly observed in a variety of applications ranging from electronic health records to network logs, with the characteristics of large-scale,…
Recently, deep learning has been advancing the state of the art in artificial intelligence to a new level, and humans rely on artificial intelligence techniques more than ever. However, even with such unprecedented advancements, the lack of…